20M Tokens FREE => Use u 20M daily allowance on top models
DeepSeek V4.1 Flash 1017 •Kimi K3 •Qwen 3.8 MAX •GLM 5.3 Flash •Gemini 3.8 Flash Works in Cursor, Claude Code, Hermes and OpenCode
DeepSeek V4.1 Flash. FREE plan.
$20 in monthly usage included 👀 How to try DeepSeek and Qwen in Perch without a paid subscription Perch lists DeepSeek V4.1 Flash on its free Starter plan. Qwen 3.8 Max is also included until November 20, 2026 at 10 PM PKT. No credit card
The town made with the Qwen 3.8 27B model running DeepSeek Harness looks pretty good too!
Especially the light and shadow effects, switching between far and near lenses, it feels like it can be played! The total cost is only 211k tokens, and the entire process is completed locally. Thanks to @loktar00 for bringing us the test!
Another side by side comparison of Qwen 3.8 Max vs. QoDuck (presumably some Qwen 4.0 variation).
Both using the same prompt and thinking level. Qwen 3.8 Max took 1 hour and 55 minutes with 137 iterations in one shot. QoDuck took 29 minutes and 30 seconds with 99 iterations in
You have reached the end of the archive
All of qwen38